Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 DAEDALUS,用自生成任务自举 Agent 记忆
Published Oct 6
Evaluated models GPT-5.4-mini , GPT-5.6 Luna , Qwen3.6-35B-A3B and others11 提出 FAO 框架,形式化隐私约束下的分布式智能体协同优化
Published Oct 1 Abstract FAO 把智能体协作写成效用、隐私和通信的多目标问题,并给出组件分类与迁移框架。Federated Agent Optimization(FAO) 是一篇框架论文:多个处在私有环境中的 LLM 智能体,如何在原始数据、完整轨迹和本地知识不离开客户端的前提下协作改进。
访谈残障成人,分析向记忆型助手披露残障时的信息流与语境完整性
Published Sep 19 综述自主渗透智能体的继承攻击、架构攻击及护栏缺口
Published Sep 15 Abstract 用双轴分类连接渗透智能体的架构、攻击与护栏,并认为现有防御仍按组件分开。这是一篇关于自主 AI 渗透测试智能体的安全综述:用架构和生命周期两轴整理威胁与护栏,不做新的攻击实验。
系统梳理智能体执行链路中的越狱攻击与防御并比较推理时防御
Published Sep 11
Evaluated models Qwen3.5-4B , Llama-3.1-8B-Instruct Abstract SoK 将越狱重放到智能体流水线,并用两种模型检验回复层防御的边际与代价。Mia 等人把越狱安全从单轮回复扩展到智能体的规划、记忆、工具和智能体间通信,并问既有结论在更强原生对齐下是否还成立。
提出内核管理共享记忆抽象,统一多智能体的检索、隐私过滤与注入
Published Sep 9
Evaluated models GPT-4o , Llama-3.1:8B , Qwen-2.5:7B Abstract 作者称内核集中管理记忆,能拿到无约束上下文的大部分个性化收益,并降低延迟。kernel-managed shared memory 把多智能体的检索、隐私和注入收进 agent-system kernel,并在 AIOS 上与三种替代方案比较。
提出离线两阶段框架,诊断易翻转步骤并生成记忆指南以稳定智能体
Published Sep 8
Evaluated models GPT-4.1 , GPT-OSS-120B Abstract 用离线一致性诊断生成记忆指南,在 AppWorld 上提高重复全通过率。作者要缩小的是 LLM 智能体平均通过、重复不稳之间的 consistency gap,即 Mean@k 减 Passˆk。
用 SAVER 框架综述自演化智能体的状态复用安全
Published Sep 8 Abstract SAVER 用状态转移追踪自演化安全:合法状态可经复用变不安全,后代修复证据仍少。SAVER 是一篇关于自演化智能体安全的转移中心综述:安全对象从单次回答或单次授权动作,转到可复用状态在多次转移中的谱系。
You have reached the end